© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91012
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    That
    -0.50
    ↵
    -0.47
    にも
    -0.47
    Then
    -0.45
    -
    -0.43
    .
    -0.43
    Before
    -0.42
    Already
    -0.41
    that
    -0.41
    Take
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.77
    ValueStyle
    0.77
     tromper
    0.76
     يتيمه
    0.74
     circulaire
    0.71
    MessageTagHelper
    0.71
     ComVisible
    0.69
    ⓧ
    0.68
    httphttps
    0.68
    AllAfrica
    0.68
    Activations Density 0.009%

    No Known Activations